© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 2710
    Prev
    Next
    INDEX
    Explanations

    animal-related terms, particularly focusing on animals like cubs, whales, and jellyfish, as well as marine ecosystems

    oai_token-act-pair · gpt-3.5-turbo

    references to specific animal species and their breeding or conservation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICT
    -0.77
    IENT
    -0.71
     billing
    -0.69
    pass
    -0.68
     ILCS
    -0.68
     Sins
    -0.67
    channelAvailability
    -0.66
    Rated
    -0.66
    Nap
    -0.65
    VERTISEMENT
    -0.65
    POSITIVE LOGITS
     species
    1.12
    fish
    1.08
     beetle
    1.06
     larvae
    1.00
     mammals
    1.00
     rodents
    0.96
     worms
    0.95
     beetles
    0.94
     animals
    0.93
     dolphins
    0.92
    Activations Density 0.345%

    No Known Activations